Pudamya commited on
Commit
6baa794
·
verified ·
1 Parent(s): db44d5d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -54,7 +54,7 @@ The model is trained **only on a large phonetic transliteration dataset**, learn
54
 
55
  ---
56
 
57
- ## 📚 Datasets Used
58
 
59
  - **Phonetic dataset**
60
  - Large-scale Singlish ↔ Sinhala phonetic pairs
@@ -65,7 +65,7 @@ All datasets were cleaned, normalized, and deduplicated before training.
65
 
66
  ---
67
 
68
- ## 📊 Evaluation Metrics
69
 
70
  The model was evaluated using standard sequence-to-sequence metrics:
71
 
@@ -84,7 +84,7 @@ The two-phase model consistently outperformed the one-phase model, especially on
84
  ```python
85
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
86
 
87
- repo = "YOUR_USERNAME/YOUR_MODEL_REPO"
88
 
89
  tokenizer = AutoTokenizer.from_pretrained(repo, use_fast=False)
90
  model = AutoModelForSeq2SeqLM.from_pretrained(repo)
 
54
 
55
  ---
56
 
57
+ ## Datasets Used
58
 
59
  - **Phonetic dataset**
60
  - Large-scale Singlish ↔ Sinhala phonetic pairs
 
65
 
66
  ---
67
 
68
+ ## Evaluation Metrics
69
 
70
  The model was evaluated using standard sequence-to-sequence metrics:
71
 
 
84
  ```python
85
  from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
86
 
87
+ repo = "Pudamya/mt5-singlish2sinhala"
88
 
89
  tokenizer = AutoTokenizer.from_pretrained(repo, use_fast=False)
90
  model = AutoModelForSeq2SeqLM.from_pretrained(repo)